© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 2972
    Prev
    Next
    INDEX
    Explanations

    the word "collection" and, less strongly, words like "most"

    oai_token-act-pair · gemini-2.0-flash

    collection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     precipit
    -0.52
    UpdateCommand
    -0.50
    ault
    -0.50
    .
    -0.49
     prof
    -0.49
    phinx
    -0.47
     instrument
    -0.45
    売
    -0.45
    reichen
    -0.45
     profits
    -0.45
    POSITIVE LOGITS
     autorytatywna
    0.98
     مشين
    0.93
    aarrggbb
    0.82
     समीक्षक
    0.81
    
    0.76
     disambiguazione
    0.74
    astify
    0.73
    SerializeField
    0.72
    Hentet
    0.71
     AssemblyCompany
    0.70
    Activations Density 0.145%

    No Known Activations